Agent skill

Liuguang Banlan UI

by sickn33 in sickn33/agentic-awesome-skills

Implements an interface in one of two named color modes, iridescent white or colorful black, from a parameterized starter that reports measured color intensity.

MITAuto-check passedFrontend & Design

Install Liuguang Banlan UI

skills CLI
$ npx skills add sickn33/agentic-awesome-skills --skill liuguang-banlan-ui -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sickn33/agentic-awesome-skills liuguang-banlan-ui --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/liuguang-banlan-ui .claude/skills/liuguang-banlan-ui && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
liuguang-banlan-ui
GitHub stars
47k
Used in
1 other repo
Token cost
~2.5k tokens
SKILL.md length
1,214 words
Files
26 (incl. scripts, references, assets)
Skills in repo
1,497
Repo updated
First seen
Licence
MIT

At a glance

Implements an interface in one of two named color modes, iridescent white or colorful black, from a parameterized starter that reports measured color intensity.

  • Works in 7 steps: Classify the request → Gate visual verification → Establish the scene and structure → …
  • A UI request names the iridescent white or colorful black mode
  • SKILL.md covers Overview, When to Use, Workflow and Limitations and capability…, plus 2 more sections
  • Runs JavaScript scripts from its folder; calls python

What it does

The skill covers two explicit modes in one implementation: 流光溢彩白 (iridescent white), mapped to the opal theme, and 五彩斑斓黑 (colorful black), mapped to obsidian. Color lives in a spectral field, map markers and state accents, while the logo, text, rules and controls stay neutral. The suggested layout is a calm three-pane workspace such as field research, inventory or monitoring, and the agent is told to adapt the existing project rather than replace its design system.

Output is parameterized with OKLCH values, peak opacity, spatial scale and phase, with a WebGL or CSS fallback. The final report gives total and per-color intensity plus measured coverage from screenshots. Before claiming visual validation, the agent checks whether it can really inspect images; if not, it still runs pixel checks but marks the result visual-unverified. Two reference files, a style contract and a verification guide, are read first, and starter assets for both themes are included.

When your agent uses it

  • A UI request names the iridescent white or colorful black mode
  • You need a reusable parameterized color starter with measured intensities
  • A final design report must list OKLCH values and screenshot measurements

Example prompts

  • “Build the inventory dashboard in the 流光溢彩白 mode and report each color's intensity.”
  • “Use the 五彩斑斓黑 theme for our monitoring screen and include the OKLCH values in the report.”
  • “Add both spectral modes to the project from one shared implementation without replacing our design system.”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Classify the request
  2. Gate visual verification
  3. Establish the scene and structure
  4. Implement the parameter contract
  5. Build the spectral field
  6. Preserve interaction and accessibility
  7. Validate and report

What it can do on your machine

Read from SKILL.md and the folder at commit 1c7bdea. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Liuguang Banlan UI loads about 2.5k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 70 tokens; SKILL.md has 1,214 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from sickn33/agentic-awesome-skills at commit 1c7bdea, republished under its MIT licence (© sickn33). 1,214 words, ~2,468 tokens.

Download SKILL.mdSave it as .claude/skills/liuguang-banlan-ui/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.
name
liuguang-banlan-ui
description
Builds two parameterized UI modes—流光溢彩白 (iridescent white) and 五彩斑斓黑 (colorful black)—with OKLCH, WebGL/CSS fallback, vision gating, screenshot QA, and total/per-color intensity reports. Use when a UI request names either mode or needs measured color parameters.
category
creative
risk
critical
source
self
source_type
self
date_added
2026-08-15
author
3516027002att-ui
tags
ui, frontend, oklch, webgl, accessibility
tools
codex, claude, cursor, gemini

流光斑斓 UI 工坊

Overview

Use one skill with two explicit modes, not a generic material library. Preserve a stable information workspace while treating the spectral field as a controlled environmental layer. Keep the implementation parameterized so every output can report total color intensity, per-color intensity, OKLCH values, peak opacity, spatial scale, phase, and measured coverage.

Read style-contract.md before choosing a mode or changing palette semantics. Read verification.md before claiming visual or screenshot validation.

When to Use

  • Use when a user names 流光溢彩白 or 五彩斑斓黑, asks for one unified skill covering both, or needs a reusable parameterized starter.
  • Use when the final report must include total color intensity, each color's intensity, OKLCH values, and screenshot measurements.
  • Do not use for a generic theme-token library or an unparameterized visual mockup.

Workflow

1. Classify the request
  • Map “流光溢彩白” to opal and “五彩斑斓黑” to obsidian.
  • If both are requested, keep one shared implementation and two explicit theme manifests.
  • Inspect the existing project, framework, route, build system, and uncommitted work before copying starter assets.
  • Use the smallest appropriate change surface; do not replace an existing design system without authorization.
2. Gate visual verification
  • Confirm that the executing model can directly inspect images before taking a screenshot-based visual claim.
  • If native image inspection is unavailable, continue with code and deterministic pixel checks but mark the result visual-unverified; never infer visual quality from DOM or CSS alone.
  • Record modelVision, screenshotCapture, deterministicPixelMetrics, and visualVerificationMode in the final report.
3. Establish the scene and structure
  • Choose a neutral, information-dense workbench domain such as field research, inventory, monitoring, or operations.
  • Use a continuous three-pane or similarly coherent workspace: navigation, queue/list, detail, metadata, and one signature observation band.
  • Keep color in the field, map markers, and state accents. Keep the logo, avatar, rules, text, controls, boundaries, and semantic hierarchy neutral; do not paint them with palette gradients.
  • Prefer restrained surfaces and weak fills. Avoid turning every region into a floating card.
4. Implement the parameter contract

Maintain a serializable manifest with these top-level fields:

js
{
  schemaVersion, mode, label, preset, seed,
  overallColorIntensity,
  base: { oklch },
  colors: [{
    id, label, oklch, srgbFallback,
    intensity, peakOpacity,
    fieldScale, phase,
    measuredCoverage, effectiveShare
  }],
  field: { scale, octaves, warpStrength, motionSpeed, staticTime, ditherStrength, luminanceCap },
  output: { colorSpace, reducedMotion }
}
  • Keep every intensity in [0, 1]; make overallColorIntensity the global budget and colors[].intensity the per-color budget. The renderer multiplies intensity by peakOpacity, so treat peakOpacity as the calibrated strength at full intensity.
  • Order colors by hue. The renderer draws six hue stops around a loop and mixes each color with its array neighbors; near-complementary neighbors mix toward gray.
  • luminanceCap applies only in obsidian. ditherStrength is the dither amplitude in output codes; 1 removes quantization bias.
  • Use OKLCH as the authoring space and provide an sRGB fallback for non-OKLCH contexts.
  • Keep the seed, static frame, phases, and field scales deterministic; do not use random per render.
  • Expose sliders for the global intensity and every configured color. Make reset, JSON export, and copy actions available.
5. Build the spectral field
  • Use a procedural fBm/domain-warp field or an equivalent continuous field; keep it behind the interface with pointer-events: none.
  • Use broad flowing hue regions or ribbons, not obvious radial blobs, spotlight circles, or hard rainbow bands.
  • Upload the complete palette and per-color field scales to the renderer. Apply the dark-mode luminance cap after palette mixing.
  • Encode output with the sRGB transfer function, dither in output codes, and quantize in the shader. A power-curve encode or a weak linear-light dither biases the output, most visibly in low-intensity fields and near black.
  • Provide a CSS fallback with comparable visual intent when WebGL is unavailable, such as one soft hue-ordered sweep calibrated against the WebGL field; do not use fixed radial spots.
  • Pause or freeze motion when the document is hidden or prefers-reduced-motion is active, and keep field time continuous so pausing and resuming do not jump.
  • Repaint after every resize. Resizing clears the canvas, and a paused field has no next frame to redraw it.
  • Keep the renderer local and dependency-light; do not require remote fonts, images, or APIs for the starter.
6. Preserve interaction and accessibility
  • Keep semantic headings, labels, focus-visible states, keyboard escape behavior, and readable contrast.
  • Test navigation, record/list selection, tab selection, parameter panel open/close, slider input, reset, export, and copy fallback.
  • Make the workbench responsive at a narrow mobile viewport; collapse navigation and metadata without losing the primary record flow.
Show full SKILL.md (522 more words)Show less
7. Validate and report
  • Scaffold a clean starter with scripts/scaffold_template.py when a neutral implementation is needed.
  • Keep theme configs as data-only assignments. The bundled parser rejects expressions, function calls, duplicate keys, trailing statements, and oversized manifests without executing JavaScript.
  • Run scripts/validate_manifest.py on each theme config before rendering, and resolve its warnings.
  • Serve previews with scripts/serve_preview.py, which disables caching, then capture desktop and mobile screenshots with a real browser. Inspect them directly if visual capability is available.
  • Run scripts/measure_preview.py on the pure field screenshot and retain measured chromatic ratio, tint, lightness shift, gray ratio, per-color coverage, and effective share.
  • Report configured parameters separately from measured values; do not imply that pixel attribution is an exact shader contribution.
  • Use partial, visual-unverified, or blocked when a required capability or native check is unavailable.

Limitations and capability states

  • WebGL is optional. The starter switches to a CSS spectral fallback when a WebGL context cannot be created or shader/program setup fails; fallback rendering is parameterized but is not pixel-identical to the shader.
  • Native image inspection and browser screenshot capture are runtime capabilities, not guaranteed by this skill. If either is unavailable, keep the result visual-unverified and report the missing capability explicitly.
  • The deterministic measurement helper requires the optional Python packages listed in scripts/requirements.txt. Without them it exits with an unavailable-capability message instead of producing a misleading report.
  • Manifests may contain 3 to 12 colors. The renderer uploads every configured entry up to that validated limit, while the shader ignores only unused capacity slots.
  • Configured values, fallback values, and measured pixel attribution describe different things; do not treat measured per-color coverage as an exact decomposition of shader energy.

Anti-pattern guardrails

  • Do not rename the two modes into a vague “reusable UI material” abstraction.
  • Do not use pure white as the only white-mode signal, black crush as the only dark-mode signal, or RGB neon as a shortcut to “colorful”.
  • Do not hide weak structure behind full-page glass, excessive blur, or giant gradients.
  • Do not report visual success from screenshot dimensions, DOM state, or static CSS alone.
  • Do not include private project names, links, repository identifiers, or source-chat contents in generated assets or reports.

Bundled resources

Use the bundled starter under assets/starter/ as a neutral base. Copy only the selected mode when integrating into an existing project, and preserve the existing project’s content and build conventions.

scripts/
  • scaffold_template.py: copy the neutral starter for opal, obsidian, or both.
  • manifest_parser.py: statically parse the restricted data-only theme manifest without executing JavaScript.
  • validate_manifest.py: validate required fields and ranges, and warn about hue order.
  • measure_preview.py: measure a rendered pure-field PNG as OKLab deviation from the configured base, including lightness shift and gray ratio. Install optional dependencies from scripts/requirements.txt when needed.
  • serve_preview.py: serve a directory locally with caching disabled.

Run python -m unittest discover -s tests after changing a script.

references/
  • style-contract.md: mode-specific visual rules, recommended parameter ranges, and calibration for pages where no panel covers the field.
  • verification.md: visual-capability gate, browser QA, pixel measurement, darkening check, and report schema.
assets/

starter/ contains a neutral static workbench, shared renderer, and both theme variants. Treat it as output material, not as documentation to paste into context wholesale.

© sickn33, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 25 other files (scripts, references, assets) in skills/liuguang-banlan-ui of sickn33/agentic-awesome-skills.

  • SKILL.md
  • assets/starter/favicon.svg
  • assets/starter/index.html
  • assets/starter/launcher.css
  • assets/starter/obsidian/index.html
  • assets/starter/obsidian/theme-config.js
  • assets/starter/obsidian/theme.css
  • assets/starter/opal/index.html
  • assets/starter/opal/theme-config.js
  • assets/starter/opal/theme.css
  • assets/starter/shared/base.css
  • assets/starter/shared/spectral-field.js
  • assets/starter/shared/workbench.js
  • references/style-contract.md
  • references/verification.md
  • … and 11 more

Open the folder on GitHubat commit 1c7bdea

Used in 1 other repository

We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in sickn33/agentic-awesome-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Liuguang Banlan UI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Liuguang Banlan UI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Liuguang Banlan UI this skillsickn33/agentic-awesome-skills47k1 repos~2.5kAutomated safety check: PassMIT
UI Design Stylingryokun6/ryos1.3k—~3.1kAutomated safety check: PassAGPL-3.0
OpenClaw Carapace UIopenclaw/clawhub9.5k—~699Automated safety check: PassMIT
UI StylingOhh-889/skyroc79513 repos~2.5kAutomated safety check: PassMIT
MCP Developmentcoollabsio/coolify63k1 repos~949Automated safety check: PassMIT
UI UX Pro Maxsaoudi-h/solar-icons19018 repos~11kAutomated safety check: NotesCustom licence

Similar skills

  • UI Design Styling

    ryokun6/ryos

    Design and style ryOS UI using the current OS theme token system, Tailwind variants, shared primitives, Aqua Glass, dark mode, and accent conventions.

    1.3k GitHub stars~3.1k tokensUpdated today
    Frontend & DesignAuto-check passed
  • OpenClaw Carapace UI

    openclaw/clawhub

    Guides UI work on OpenClaw apps so it uses the shared Carapace package: semantic design tokens, theme foundations, shared CSS classes and the product's existing local components.

    9.5k GitHub stars~699 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • UI Styling

    Ohh-889/skyroc

    Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs.

    795 GitHub starsUsed in 13 repos~2.5k tokens
    Frontend & DesignAuto-check passed
  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed
  • UI UX Pro Max

    saoudi-h/solar-icons

    UI/UX design intelligence for web and mobile. An agent skill from saoudi-h/solar-icons.

    190 GitHub starsUsed in 18 repos~11k tokens
    Frontend & DesignAuto-check: notes
  • Tailwind Theme Builder

    jezweb/claude-skills

    Set up Tailwind v4 + shadcn/ui themed UI with dark mode. An agent skill from jezweb/claude-skills.

    1.1k GitHub starsUsed in 1 repo~3.2k tokens
    Frontend & DesignAuto-check passed

More from sickn33/agentic-awesome-skills

All 1,497 skills in this repo
  • User Thoughts Memory

    sickn33/agentic-awesome-skills

    Saves a user's project decisions, rules and preferences into a project-local mdbase so later sessions and other agents can recover the intent.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Using LWC Memory and Graphs

    sickn33/agentic-awesome-skills

    Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.

    47k GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed
  • Find Complementary Founders

    sickn33/agentic-awesome-skills

    Guides an agent through assessing its own owner for cofounder fit, publishing an approved profile, and ranking complementary profiles other agents published for their owners.

    47k GitHub starsUsed in 1 repo~4.8k tokens
    Auto-check passed
  • Whatsapp Cloud API

    sickn33/agentic-awesome-skills

    Integracao com WhatsApp Business Cloud API (Meta). An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~4.5k tokens
    Auto-check passed
  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed
  • Content Creator

    sickn33/agentic-awesome-skills

    Drafts and reviews audience-specific content from supplied brand examples, with local scripts for brand voice and SEO diagnostics, channel templates and a content calendar.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

Questions about Liuguang Banlan UI

What does Liuguang Banlan UI do?

Implements an interface in one of two named color modes, iridescent white or colorful black, from a parameterized starter that reports measured color intensity. The skill covers two explicit modes in one implementation: 流光溢彩白 (iridescent white), mapped to the opal theme, and 五彩斑斓黑 (colorful black), mapped to obsidian. Color lives in a spectral field, map markers and state accents, while the logo, text, rules and controls stay neutral.

When should I use Liuguang Banlan UI?

Liuguang Banlan UI fits situations like: A UI request names the iridescent white or colorful black mode; you need a reusable parameterized color starter with measured intensities; A final design report must list OKLCH values and screenshot measurements.

How do I install Liuguang Banlan UI in Claude Code?

Run `npx skills add sickn33/agentic-awesome-skills --skill liuguang-banlan-ui -a claude-code`. Or copy the skill folder (skills/liuguang-banlan-ui in sickn33/agentic-awesome-skills) into .claude/skills/liuguang-banlan-ui in your project. Claude Code loads it when a task matches its description.

How do I install Liuguang Banlan UI in Codex?

Run `npx skills add sickn33/agentic-awesome-skills --skill liuguang-banlan-ui -a codex`. Or copy the skill folder (skills/liuguang-banlan-ui in sickn33/agentic-awesome-skills) into .agents/skills/liuguang-banlan-ui in your project. Codex loads it when a task matches its description.

Can I use Liuguang Banlan UI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sickn33/agentic-awesome-skills --skill liuguang-banlan-ui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/liuguang-banlan-ui, .gemini/skills/liuguang-banlan-ui, .github/skills/liuguang-banlan-ui and .opencode/skills/liuguang-banlan-ui in your project.

What does Liuguang Banlan UI need to run?

Going by SKILL.md and its folder, Liuguang Banlan UI needs JavaScript for the scripts in its folder and the command-line tools its instructions call (python).

Does Liuguang Banlan UI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Liuguang Banlan UI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Liuguang Banlan UI use?

Liuguang Banlan UI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Liuguang Banlan UI use?

About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Liuguang Banlan UI?

Skills that share tags, products or a category with Liuguang Banlan UI: UI Design Styling (ryokun6/ryos, 1.3k stars), OpenClaw Carapace UI (openclaw/clawhub, 9.5k stars), UI Styling (Ohh-889/skyroc, 795 stars) and MCP Development (coollabsio/coolify, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Liuguang Banlan UI?

sickn33 (a GitHub user) maintains it in sickn33/agentic-awesome-skills, which has 47,443 GitHub stars. The repository holds 1,497 skills in this directory. The repository was last updated on October 10, 2026.

Source: sickn33/agentic-awesome-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.